© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13915
    Prev
    Next
    INDEX
    Explanations

    syrup, liquor, vodka, paste formulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abl
    -0.07
     policing
    -0.06
    seo
    -0.06
    als
    -0.06
     Hash
    -0.06
    .har
    -0.06
     microf
    -0.06
     Det
    -0.06
    æľ¨é©¬
    -0.06
    çĶ¨çº¸
    -0.06
    POSITIVE LOGITS
    Containing
    0.09
    centes
    0.08
    æīĢåIJ«
    0.08
     chứa
    0.08
    åIJ«æľīçļĦ
    0.08
     containing
    0.08
    ä¾ĨæºIJ
    0.08
    cente
    0.08
     concentrate
    0.08
     handy
    0.08
    Activations Density 0.054%

    No Known Activations